poster

Automatic datatype generation and optimization

Authors:

Fredrik Kjolstad,

Torsten Hoefler,

Marc SnirAuthors Info & Claims

PPoPP '12: Proceedings of the 17th ACM SIGPLAN symposium on Principles and Practice of Parallel Programming

Pages 327 - 328

https://doi.org/10.1145/2145816.2145878

Published: 25 February 2012 Publication History

Get Access

Abstract

Many high performance applications spend considerable time packing noncontiguous data into contiguous communication buffers. MPI Datatypes provide an alternative by describing noncontiguous data layouts. This allows sophisticated hardware to retrieve data directly from application data structures. However, packing codes in real-world applications are often complex and specifying equivalent datatypes is difficult, time-consuming, and error prone. We present an algorithm that automates the transformation. We have implemented the algorithm in a tool that transforms packing code to MPI Datatypes, and evaluated it by transforming 90 packing codes from the NAS Parallel Benchmarks. The transformation allows easy porting of applications to new machines that benefit from datatypes, thus improving programmer productivity.

References

[1]

Automatic datatype generation tool download. URL http://people.csail.mit.edu/fred/datatypes. Last Accessed 12/17/2011.

Google Scholar

[2]

D. Bailey, T. Harris, W. Saphir, R. Wijngaart, A. Woo, and M. Yarrow. The NAS parallel benchmarks 2.0. Technical report, NASA, 1995.

Google Scholar

[3]

F. Kjolstad, T. Hoefler, and M. Snir. A transformation to convert packing code to compact datatypes for efficient zero-copy data transfer. Technical report, University of Illinois at Urbana-Champaign, 2011.

Google Scholar

[4]

R. Ross, N. Miller, and W. Gropp. Implementing fast and reusable datatype processing. In EuroPVM/MPI, 2003.

Crossref

Google Scholar

[5]

G. Santhanaraman, J. Wu, and D. K. Panda. Zero-copy MPI derived datatype communication over InfiniBand. In EuroPVM/MPI, 2004.

Crossref

Google Scholar

[6]

W. Tansey and E. Tilevich. Efficient automated marshaling of C++ data structures for MPI applications. In IPDPS, 2008.

Crossref

Google Scholar

Cited By

View all

Xiong QBangalore PSkjellum AHerbordt M(2018)MPI Derived DatatypesProceedings of the 25th European MPI Users' Group Meeting10.1145/3236367.3236378(1-10)Online publication date: 23-Sep-2018
https://dl.acm.org/doi/10.1145/3236367.3236378
Marrinan TInsley JRizzi STessier FPapka M(2017)Automated Dynamic Data Redistribution2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)10.1109/IPDPSW.2017.17(1208-1215)Online publication date: May-2017
https://doi.org/10.1109/IPDPSW.2017.17
Carpen-Amarie AHunold STräff JDongarra JHolmes DCollis ALarsson Träff JSmith L(2016)On the Expected and Observed Communication Performance with MPI Derived DatatypesProceedings of the 23rd European MPI Users' Group Meeting10.1145/2966884.2966905(108-120)Online publication date: 25-Sep-2016
https://dl.acm.org/doi/10.1145/2966884.2966905
Show More Cited By

Index Terms

Automatic datatype generation and optimization
1. Computing methodologies
  1. Parallel computing methodologies
    1. Parallel programming languages
2. Software and its engineering
  1. Software notations and tools
    1. General programming languages
      1. Language types
        Parallel programming languages

Recommendations

Automatic datatype generation and optimization
PPOPP '12

Many high performance applications spend considerable time packing noncontiguous data into contiguous communication buffers. MPI Datatypes provide an alternative by describing noncontiguous data layouts. This allows sophisticated hardware to retrieve ...
Ornaments: exploiting parametricity for safer, more automated code refactorization and code reuse (invited talk)
Haskell '17

Inductive datatypes and parametric polymorphism are two key features introduced in the ML family of languages, which have already been widely exploited for structuring programs: Haskell and ML programs are often more elegant and more correct by ...
Extended MPICC to generate MPI derived datatypes from C datatypes automatically
PVM/MPI'07: Proceedings of the 14th European conference on Recent Advances in Parallel Virtual Machine and Message Passing Interface

More and more MPI programs are developed by people who are not experienced parallel programmers; many others are automatically generated by specific frameworks. For both cases, MPI derived datatypes are difficult to handle. This article presents MPIECC, ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

PPoPP '12: Proceedings of the 17th ACM SIGPLAN symposium on Principles and Practice of Parallel Programming

February 2012

352 pages

ISBN:9781450311601

DOI:10.1145/2145816

General Chair:
J. Ramanujam
Louisiana State University, USA
,
Program Chair:
P. Sadayappan
The Ohio State University, USA

ACM SIGPLAN Notices Volume 47, Issue 8
PPOPP '12
August 2012
334 pages
ISSN:0362-1340
EISSN:1558-1160
DOI:10.1145/2370036
Issue’s Table of Contents

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 25 February 2012

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Poster

Conference

PPoPP '12

Sponsor:

SIGPLAN

PPoPP '12: ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming

February 25 - 29, 2012

Louisiana, New Orleans, USA

Acceptance Rates

Overall Acceptance Rate 230 of 1,014 submissions, 23%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

12
Total Citations
View Citations
186
Total Downloads

Downloads (Last 12 months)9
Downloads (Last 6 weeks)1

Reflects downloads up to 12 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Xiong QBangalore PSkjellum AHerbordt M(2018)MPI Derived DatatypesProceedings of the 25th European MPI Users' Group Meeting10.1145/3236367.3236378(1-10)Online publication date: 23-Sep-2018
https://dl.acm.org/doi/10.1145/3236367.3236378
Marrinan TInsley JRizzi STessier FPapka M(2017)Automated Dynamic Data Redistribution2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)10.1109/IPDPSW.2017.17(1208-1215)Online publication date: May-2017
https://doi.org/10.1109/IPDPSW.2017.17
Carpen-Amarie AHunold STräff JDongarra JHolmes DCollis ALarsson Träff JSmith L(2016)On the Expected and Observed Communication Performance with MPI Derived DatatypesProceedings of the 23rd European MPI Users' Group Meeting10.1145/2966884.2966905(108-120)Online publication date: 25-Sep-2016
https://dl.acm.org/doi/10.1145/2966884.2966905
Komuravelli RSinclair MAlsop JHuzaifa MKotsifakou MSrivastava PAdve SAdve V(2015)StashACM SIGARCH Computer Architecture News10.1145/2872887.275037443:3S(707-719)Online publication date: 13-Jun-2015
https://dl.acm.org/doi/10.1145/2872887.2750374
Kalany MTräff JDongarra JDenis AGoglin BJeannot EMercier G(2015)Efficient, Optimal MPI Datatype Reconstruction for Vector and Index TypesProceedings of the 22nd European MPI Users' Group Meeting10.1145/2802658.2802671(1-10)Online publication date: 21-Sep-2015
https://dl.acm.org/doi/10.1145/2802658.2802671
Komuravelli RSinclair MAlsop JHuzaifa MKotsifakou MSrivastava PAdve SAdve VMarr DAlbonesi D(2015)StashProceedings of the 42nd Annual International Symposium on Computer Architecture10.1145/2749469.2750374(707-719)Online publication date: 13-Jun-2015
https://dl.acm.org/doi/10.1145/2749469.2750374
Träff JDongarra JIshikawa YHori A(2014)Optimal MPI Datatype Normalization for Vector and Index-block TypesProceedings of the 21st European MPI Users' Group Meeting10.1145/2642769.2642771(33-38)Online publication date: 9-Sep-2014
https://dl.acm.org/doi/10.1145/2642769.2642771
Schneider TGerstenberger RHoefler T(2014)Compiler Optimizations for Non-contiguous Remote Data MovementLanguages and Compilers for Parallel Computing10.1007/978-3-319-09967-5_18(307-321)Online publication date: 1-Oct-2014
https://doi.org/10.1007/978-3-319-09967-5_18
Schneider TKjolstad FHoefler TDongarra JBlas JCarretero J(2013)MPI datatype processing using runtime compilationProceedings of the 20th European MPI Users' Group Meeting10.1145/2488551.2488552(19-24)Online publication date: 15-Sep-2013
https://dl.acm.org/doi/10.1145/2488551.2488552
Gropp W(2012)MPI 3 and beyondProceedings of the 19th European conference on Recent Advances in the Message Passing Interface10.1007/978-3-642-33518-1_1(1-9)Online publication date: 23-Sep-2012
https://dl.acm.org/doi/10.1007/978-3-642-33518-1_1
Show More Cited By

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Automatic datatype generation and optimization

Ornaments: exploiting parametricity for safer, more automated code refactorization and code reuse (invited talk)

Extended MPICC to generate MPI derived datatypes from C datatypes automatically